Deep Image Prior for photoacoustic tomography can mitigate limited-view artifacts

2026-04-21

AI Summary

This work addresses the challenge of artifacts arising from limited-view acquisition and noise in photoacoustic tomography by proposing an unsupervised reconstruction method based on Deep Image Prior (DIP). For the first time, DIP is successfully adapted to limited-view photoacoustic imaging, integrating fast forward and adjoint operators, total variation regularization, and an efficient inverse initialization scheme to achieve robust reconstructions without requiring ground-truth labels. Quantitative evaluation using a digital twin framework demonstrates that the proposed method significantly outperforms conventional total variation-based approaches on both simulated and experimental data, effectively suppressing artifacts and enhancing overall image quality.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

We study the deep image prior (DIP) framework applied to photoacoustic tomography (PAT) as an unsupervised reconstruction approach to mitigate limited-view artifacts and noise commonly encountered in experimental settings. Efficient implementation is achieved by employing recently published fast forward and adjoint algorithms for circular measurement geometries. Initialization via a fast inverse and total variation (TV) regularization are applied to further suppress noise and mitigate overfitting. For comparison, we compute a classical TV reconstruction. Our experiments comprise simulated PAT measurements under limited-view geometries and varying levels of added noise as well as experimental measurements together with using a digital twin for quality assessment. Our findings suggest that DIP framework provides an effective unsupervised strategy for robust PAT reconstruction even in the challenging case of a limited view geometry providing improvement in several quantitative measures over total variation reconstructions.

Problem

• photoacoustic tomography
• limited-view artifacts
• image reconstruction
• noise mitigation

Innovation

• Deep Image Prior
• Photoacoustic Tomography
• Limited-View Artifacts
• Unsupervised Reconstruction
• Total Variation Regularization